Alexi Gladstone

Hey I’m Alexi!

I’m currently working on understanding intelligence by exploring different directions like Generative Modeling, Energy-Based Models, Generalization, World Models, Reasoning, Robotics, Representation Learning, and Memory.

When I’m not working, I love working out (I do a mix of powerlifting, calisthenics, and bodybuilding), running, playing random sports, and doing sidequests.

When I have time, I like reading about computational neuroscience, neuroscience, physics, psychology, philosophy, and a bunch of other stuff.

I’m always open to collaboration or chatting! Feel free to reach out to me at alexigladstone at gmail dot com to discuss anything related to research, blogs, or life!

things I’ve done

• Made Energy-Based Models Good
• Found a Third Pretraining Axis
• Figured Out the Meaning of Life

research highlights

• Energy-Based Transformers are Scalable Learners and Thinkers (ICLR Oral, ~top 1%)
• Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
• You Don’t Need Strong Assumptions: Visual Representation Learning via Temporal Differences